{"id":"https://openalex.org/W4372260017","doi":"https://doi.org/10.1109/icassp49357.2023.10096039","title":"LeanSpeech: The Microsoft Lightweight Speech Synthesis System for Limmits Challenge 2023","display_name":"LeanSpeech: The Microsoft Lightweight Speech Synthesis System for Limmits Challenge 2023","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260017","doi":"https://doi.org/10.1109/icassp49357.2023.10096039"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096039","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096039","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120779464","display_name":"Chen Zhang","orcid":"https://orcid.org/0009-0004-3596-4683"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN","US"],"is_corresponding":true,"raw_author_name":"Chen Zhang","raw_affiliation_strings":["Microsoft Azure Speech,China","Microsoft Azure Speech, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Azure Speech,China","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Azure Speech, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114889726","display_name":"Shubham Bansal","orcid":"https://orcid.org/0000-0002-8754-1074"},"institutions":[{"id":"https://openalex.org/I4210162141","display_name":"Microsoft (India)","ror":"https://ror.org/04ww0w091","country_code":"IN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210162141"]},{"id":"https://openalex.org/I4210124949","display_name":"Microsoft Research (India)","ror":"https://ror.org/02w7f3w92","country_code":"IN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210124949"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shubham Bansal","raw_affiliation_strings":["Microsoft Azure Speech,India","Microsoft Azure Speech, India"],"affiliations":[{"raw_affiliation_string":"Microsoft Azure Speech,India","institution_ids":["https://openalex.org/I4210124949","https://openalex.org/I4210162141"]},{"raw_affiliation_string":"Microsoft Azure Speech, India","institution_ids":["https://openalex.org/I4210124949"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071878605","display_name":"Aakash Lakhera","orcid":null},"institutions":[{"id":"https://openalex.org/I4210162141","display_name":"Microsoft (India)","ror":"https://ror.org/04ww0w091","country_code":"IN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210162141"]},{"id":"https://openalex.org/I4210124949","display_name":"Microsoft Research (India)","ror":"https://ror.org/02w7f3w92","country_code":"IN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210124949"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Aakash Lakhera","raw_affiliation_strings":["Microsoft Azure Speech,India","Microsoft Azure Speech, India"],"affiliations":[{"raw_affiliation_string":"Microsoft Azure Speech,India","institution_ids":["https://openalex.org/I4210124949","https://openalex.org/I4210162141"]},{"raw_affiliation_string":"Microsoft Azure Speech, India","institution_ids":["https://openalex.org/I4210124949"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041283996","display_name":"Jinzhu Li","orcid":"https://orcid.org/0000-0002-8835-8837"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]},{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Jinzhu Li","raw_affiliation_strings":["Microsoft Azure Speech,China","Microsoft Azure Speech, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Azure Speech,China","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Azure Speech, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107031356","display_name":"Gang Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]},{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Gang Wang","raw_affiliation_strings":["Microsoft Azure Speech,China","Microsoft Azure Speech, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Azure Speech,China","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Azure Speech, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043060774","display_name":"Sandeepkumar Satpal","orcid":null},"institutions":[{"id":"https://openalex.org/I4210162141","display_name":"Microsoft (India)","ror":"https://ror.org/04ww0w091","country_code":"IN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210162141"]},{"id":"https://openalex.org/I4210124949","display_name":"Microsoft Research (India)","ror":"https://ror.org/02w7f3w92","country_code":"IN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210124949"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sandeepkumar Satpal","raw_affiliation_strings":["Microsoft Azure Speech,India","Microsoft Azure Speech, India"],"affiliations":[{"raw_affiliation_string":"Microsoft Azure Speech,India","institution_ids":["https://openalex.org/I4210124949","https://openalex.org/I4210162141"]},{"raw_affiliation_string":"Microsoft Azure Speech, India","institution_ids":["https://openalex.org/I4210124949"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100329353","display_name":"Sheng Zhao","orcid":"https://orcid.org/0000-0002-9624-5381"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Sheng Zhao","raw_affiliation_strings":["Microsoft Azure Speech,China","Microsoft Azure Speech, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Azure Speech,China","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Azure Speech, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061724331","display_name":"Lei He","orcid":"https://orcid.org/0000-0003-3028-6305"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Lei He","raw_affiliation_strings":["Microsoft Azure Speech,China","Microsoft Azure Speech, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Azure Speech,China","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Azure Speech, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5120779464"],"corresponding_institution_ids":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"],"apc_list":null,"apc_paid":null,"fwci":0.1746,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.52295147,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7481024265289307},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6182110905647278},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.5891373157501221},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5778990387916565},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4643346071243286},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4494306445121765},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4325956404209137},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1472868025302887},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.10675257444381714}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7481024265289307},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6182110905647278},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5891373157501221},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5778990387916565},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4643346071243286},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4494306445121765},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4325956404209137},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1472868025302887},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10675257444381714}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096039","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096039","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8600000143051147,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W147745886","https://openalex.org/W2963300588","https://openalex.org/W2963736842","https://openalex.org/W3033411150","https://openalex.org/W3195366750","https://openalex.org/W4395957972","https://openalex.org/W6606037758","https://openalex.org/W6778823374","https://openalex.org/W6803425590"],"related_works":["https://openalex.org/W2275988210","https://openalex.org/W2385621972","https://openalex.org/W2789919619","https://openalex.org/W2293457016","https://openalex.org/W2973019895","https://openalex.org/W4304195479","https://openalex.org/W4385573012","https://openalex.org/W3162414783","https://openalex.org/W3161109662","https://openalex.org/W3153768731"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"the":[3,27,79,91,94],"Microsoft":[4],"Text-to-Speech":[5],"(TTS)":[6],"system:":[7],"LeanSpeech":[8],"for":[9],"LIMMITS":[10],"(Lightweight,":[11],"Multi-speaker,":[12],"Multi-lingual":[13],"Indic":[14],"TTS)":[15],"Challenge":[16],"2023<sup":[17],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[18],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>,":[19],"which":[20,48,89],"is":[21,49,65],"part":[22],"of":[23,29,42,78,93],"ICASSP2023":[24],"to":[25],"encourage":[26],"advance":[28],"TTS":[30],"in":[31,69],"Indian":[32],"Languages.":[33],"We":[34],"propose":[35],"a":[36,55],"lightweight":[37],"encoder-decoder":[38],"acoustic":[39],"model":[40,96],"composed":[41],"1-D":[43],"convolution":[44],"and":[45,67,73,86,97],"LSTM":[46],"blocks,":[47],"trained":[50],"with":[51],"knowledge":[52],"distillation":[53],"from":[54],"multi-speaker":[56],"multi-lingual":[57],"teacher":[58],"model,":[59],"DelightfulTTS":[60],"[1].":[61],"The":[62],"speech":[63],"corpus":[64],"reprocessed":[66],"used":[68],"both":[70],"AM":[71],"training":[72,98],"vocoder":[74],"fine-tuning.":[75],"In":[76],"Track-2":[77],"challenge,":[80],"our":[81],"system":[82],"achieves":[83],"MOS":[84],"4.56":[85],"SMOS":[87],"3.98,":[88],"indicates":[90],"efficiency":[92],"proposed":[95],"strategy.":[99]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-24T23:09:58.560324","created_date":"2025-10-10T00:00:00"}